Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sz
    -0.08
     whimsical
    -0.08
    -ups
    -0.08
     Bean
    -0.07
     целях
    -0.07
     sant
    -0.07
     meticulous
    -0.07
     fréqu
    -0.07
     penser
    -0.07
    ARRIER
    -0.07
    POSITIVE LOGITS
    Formula
    0.10
    _formula
    0.09
     formula
    0.09
    formula
    0.08
     सूत्र
    0.08
     рассчиты
    0.08
    omod
    0.08
     콘
    0.08
    公式
    0.08
     Formula
    0.08
    Act Density 0.009%

    No Known Activations